classify images on fpga using quantized neural network -凯发k8网页登录
this example shows how to use deep learning hdl toolbox™ to deploy a quantized deep convolutional neural network (cnn) to an fpga. in the example you use the pretrained resnet-18 cnn to perform transfer learning and quantization. you then deploy the quantized network and use matlab ® to retrieve the prediction results.
resnet-18 has been trained on over a million images and can classify images into 1000 object categories, such as keyboard, coffee mug, pencil, and many animals. the network has learned rich feature representations for a wide range of images. the network takes an image as input and outputs a label for the object in the image together with the probabilities for each of the object categories.
for this example, you need:
deep learning toolbox™
deep learning hdl toolbox™
deep learning toolbox model for resnet-18 network
deep learning hdl toolbox™ support package for xilinx® fpga and soc devices
image processing toolbox™
deep learning toolbox model quantization library
matlab® coder™ interface for deep learning
to perform classification on a new set of images, you fine-tune a pretrained resnet-18 cnn by transfer learning. in transfer learning, you can take a pretrained network and use it as a starting point to learn a new task. fine-tuning a network with transfer learning is usually much faster and easier than training a network with randomly initialized weights. you can quickly transfer learned features to a new task using a smaller number of training images.
load pretrained network
load the pretrained resnet-18 network.
net = resnet18;
view the layers of the pretrained network.
deepnetworkdesigner(net);
the first layer, the image input layer, requires input images of size 227-by-227-by-3, where three is the number of color channels.
inputsize = net.layers(1).inputsize;
load data
this example uses the mathworks merchdata data set. this is a small data set containing 75 images of mathworks merchandise, belonging to five different classes (cap, cube, playing cards, screwdriver, and torch).
curdir = pwd; unzip('merchdata.zip'); imds = imagedatastore('merchdata', ... 'includesubfolders',true, ... 'labelsource','foldernames');
specify training and validation sets
divide the data into training and validation data sets, so that 30% percent of the images go to the training data set and 70% of the images to the validation data set. spliteachlabel splits the datastore imds into two new datastores, imdstrain and imdsvalidation.
[imdstrain,imdsvalidation] = spliteachlabel(imds,0.7,'randomized');replace final layers
to retrain resnet-18 to classify new images, replace the last fully connected layer and final classification layer of the network. in resnet-18 , these layers have the names 'fc1000' and 'classificationlayer_predictions', respectively. the fully connected layer and classification layer of the pretrained network net are configured for 1000 classes. these two layers fc1000 and classificationlayer_predictions in resnet-18, contain information on how to combine the features that the network extracts into class probabilities and predicted labels. these two layers must be fine-tuned for the new classification problem. extract all the layers, except the last two layers, from the pretrained network.
lgraph = layergraph(net)
lgraph =
layergraph with properties:
inputnames: {'data'}
outputnames: {'classificationlayer_predictions'}
layers: [71×1 nnet.cnn.layer.layer]
connections: [78×2 table]
numclasses = numel(categories(imdstrain.labels))
numclasses = 5
newlearnablelayer = fullyconnectedlayer(numclasses, ... 'name','new_fc', ... 'weightlearnratefactor',10, ... 'biaslearnratefactor',10); lgraph = replacelayer(lgraph,'fc1000',newlearnablelayer); newclasslayer = classificationlayer('name','new_classoutput'); lgraph = replacelayer(lgraph,'classificationlayer_predictions',newclasslayer);
prepare data for training
the network requires input images of size 224-by-224-by-3, but the images in the image datastores have different sizes. use an augmented image datastore to automatically resize the training images. specify additional augmentation operations to perform on the training images, such as randomly flipping the training images along the vertical axis and randomly translating them up to 30 pixels horizontally and vertically. data augmentation helps prevent the network from overfitting and memorizing the exact details of the training images.
pixelrange = [-30 30]; imageaugmenter = imagedataaugmenter( ... 'randxreflection',true, ... 'randxtranslation',pixelrange, ... 'randytranslation',pixelrange);
to automatically resize the validation images without performing further data augmentation, use an augmented image datastore without specifying any additional preprocessing operations.
augimdstrain = augmentedimagedatastore(inputsize(1:2),imdstrain, ... 'dataaugmentation',imageaugmenter); augimdsvalidation = augmentedimagedatastore(inputsize(1:2),imdsvalidation);
specify training options
specify the training options. for transfer learning, keep the features from the early layers of the pretrained network (the transferred layer weights). to slow down learning in the transferred layers, set the initial learning rate to a small value. specify the mini-batch size and validation data. the software validates the network every validationfrequency iterations during training.
options = trainingoptions('sgdm', ... 'minibatchsize',10, ... 'maxepochs',6, ... 'initiallearnrate',1e-4, ... 'shuffle','every-epoch', ... 'validationdata',augimdsvalidation, ... 'validationfrequency',3, ... 'verbose',false, ... 'plots','training-progress');
train network
train the network that consists of the transferred and new layers. by default, trainnetwork uses a gpu if one is available. using this function on a gpu requires parallel computing toolbox™ and a supported gpu device. for more information, see gpu computing requirements (parallel computing toolbox). if a gpu is not available, the network uses a cpu (requires matlab coder interface for deep learning). you can also specify the execution environment by using the executionenvironment name-value argument of trainingoptions.
nettransfer = trainnetwork(augimdstrain,lgraph,options);
quantize network
quantize the network using the dlquantizer object. set the target execution environment to fpga.
dlquantobj = dlquantizer(nettransfer,'executionenvironment','fpga');
calibrate quantized network
use the calibrate function to exercise the network with sample inputs and collect the range information. the calibrate function collects the dynamic ranges of the weights and biases in the convolution and fully connected layers of the network and the dynamic ranges of the activations in all layers of the network. the function returns the information as a table, in which each row contains range information for a learnable parameter of the quantized network.
calibrate(dlquantobj,augimdstrain)
ans=95×5 table
optimized layer name network layer name learnables / activations minvalue maxvalue
__________________________ __________________ ________________________ ________ ________
{'conv1_weights' } {'conv1' } "weights" -0.79143 1.2547
{'conv1_bias' } {'conv1' } "bias" -0.66949 0.67671
{'res2a_branch2a_weights'} {'res2a_branch2a'} "weights" -0.42074 0.34251
{'res2a_branch2a_bias' } {'res2a_branch2a'} "bias" -0.8039 1.2488
{'res2a_branch2b_weights'} {'res2a_branch2b'} "weights" -0.78524 0.59222
{'res2a_branch2b_bias' } {'res2a_branch2b'} "bias" -1.3835 1.7661
{'res2b_branch2a_weights'} {'res2b_branch2a'} "weights" -0.3174 0.33645
{'res2b_branch2a_bias' } {'res2b_branch2a'} "bias" -1.1203 1.5238
{'res2b_branch2b_weights'} {'res2b_branch2b'} "weights" -1.1915 0.93059
{'res2b_branch2b_bias' } {'res2b_branch2b'} "bias" -0.81928 1.2022
{'res3a_branch2a_weights'} {'res3a_branch2a'} "weights" -0.19735 0.22659
{'res3a_branch2a_bias' } {'res3a_branch2a'} "bias" -0.53009 0.69532
{'res3a_branch2b_weights'} {'res3a_branch2b'} "weights" -0.53557 0.72768
{'res3a_branch2b_bias' } {'res3a_branch2b'} "bias" -0.67756 1.1733
{'res3a_branch1_weights' } {'res3a_branch1' } "weights" -0.63395 0.97791
{'res3a_branch1_bias' } {'res3a_branch1' } "bias" -0.95277 0.75618
⋮
define fpga board interface
define the target fpga board programming interface by using the dlhdl.target object. create a programming interface with custom name for your target device and an ethernet interface to connect the target device to the host computer.
htarget = dlhdl.target('xilinx','interface','ethernet');
prepare network for deployment
prepare the network for deployment by creating a dlhdl.workflow object. specify the network and bitstream name. ensure that the bitstream name matches the data type and the fpga board that you are targeting. in this example, the target fpga board is the xilinx® zynq® ultrascale ™ mpsoc zcu102 board and the bitstream uses the int8 data type.
hw = dlhdl.workflow(network=dlquantobj,bitstream='zcu102_int8',target=htarget);compile network
run the compile method of the dlhdl.workflow object to compile the network and generate the instructions, weights, and biases for deployment.
dn = compile(hw,'inputframenumberlimit',15)### compiling network for deep learning fpga prototyping ...
### targeting fpga bitstream zcu102_int8.
### optimizing network: fused 'nnet.cnn.layer.batchnormalizationlayer' into 'nnet.cnn.layer.convolution2dlayer'
### the network includes the following layers:
1 'data' image input 224×224×3 images with 'zscore' normalization (sw layer)
2 'conv1' 2-d convolution 64 7×7×3 convolutions with stride [2 2] and padding [3 3 3 3] (hw layer)
3 'conv1_relu' relu relu (hw layer)
4 'pool1' 2-d max pooling 3×3 max pooling with stride [2 2] and padding [1 1 1 1] (hw layer)
5 'res2a_branch2a' 2-d convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
6 'res2a_branch2a_relu' relu relu (hw layer)
7 'res2a_branch2b' 2-d convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
8 'res2a' addition element-wise addition of 2 inputs (hw layer)
9 'res2a_relu' relu relu (hw layer)
10 'res2b_branch2a' 2-d convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
11 'res2b_branch2a_relu' relu relu (hw layer)
12 'res2b_branch2b' 2-d convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
13 'res2b' addition element-wise addition of 2 inputs (hw layer)
14 'res2b_relu' relu relu (hw layer)
15 'res3a_branch2a' 2-d convolution 128 3×3×64 convolutions with stride [2 2] and padding [1 1 1 1] (hw layer)
16 'res3a_branch2a_relu' relu relu (hw layer)
17 'res3a_branch2b' 2-d convolution 128 3×3×128 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
18 'res3a_branch1' 2-d convolution 128 1×1×64 convolutions with stride [2 2] and padding [0 0 0 0] (hw layer)
19 'res3a' addition element-wise addition of 2 inputs (hw layer)
20 'res3a_relu' relu relu (hw layer)
21 'res3b_branch2a' 2-d convolution 128 3×3×128 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
22 'res3b_branch2a_relu' relu relu (hw layer)
23 'res3b_branch2b' 2-d convolution 128 3×3×128 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
24 'res3b' addition element-wise addition of 2 inputs (hw layer)
25 'res3b_relu' relu relu (hw layer)
26 'res4a_branch2a' 2-d convolution 256 3×3×128 convolutions with stride [2 2] and padding [1 1 1 1] (hw layer)
27 'res4a_branch2a_relu' relu relu (hw layer)
28 'res4a_branch2b' 2-d convolution 256 3×3×256 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
29 'res4a_branch1' 2-d convolution 256 1×1×128 convolutions with stride [2 2] and padding [0 0 0 0] (hw layer)
30 'res4a' addition element-wise addition of 2 inputs (hw layer)
31 'res4a_relu' relu relu (hw layer)
32 'res4b_branch2a' 2-d convolution 256 3×3×256 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
33 'res4b_branch2a_relu' relu relu (hw layer)
34 'res4b_branch2b' 2-d convolution 256 3×3×256 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
35 'res4b' addition element-wise addition of 2 inputs (hw layer)
36 'res4b_relu' relu relu (hw layer)
37 'res5a_branch2a' 2-d convolution 512 3×3×256 convolutions with stride [2 2] and padding [1 1 1 1] (hw layer)
38 'res5a_branch2a_relu' relu relu (hw layer)
39 'res5a_branch2b' 2-d convolution 512 3×3×512 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
40 'res5a_branch1' 2-d convolution 512 1×1×256 convolutions with stride [2 2] and padding [0 0 0 0] (hw layer)
41 'res5a' addition element-wise addition of 2 inputs (hw layer)
42 'res5a_relu' relu relu (hw layer)
43 'res5b_branch2a' 2-d convolution 512 3×3×512 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
44 'res5b_branch2a_relu' relu relu (hw layer)
45 'res5b_branch2b' 2-d convolution 512 3×3×512 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
46 'res5b' addition element-wise addition of 2 inputs (hw layer)
47 'res5b_relu' relu relu (hw layer)
48 'pool5' 2-d global average pooling 2-d global average pooling (hw layer)
49 'new_fc' fully connected 5 fully connected layer (hw layer)
50 'prob' softmax softmax (sw layer)
51 'new_classoutput' classification output crossentropyex with 'mathworks cap' and 4 other classes (sw layer)
### notice: the layer 'data' with type 'nnet.cnn.layer.imageinputlayer' is implemented in software.
### notice: the layer 'prob' with type 'nnet.cnn.layer.softmaxlayer' is implemented in software.
### notice: the layer 'new_classoutput' with type 'nnet.cnn.layer.classificationoutputlayer' is implemented in software.
### compiling layer group: conv1>>pool1 ...
### compiling layer group: conv1>>pool1 ... complete.
### compiling layer group: res2a_branch2a>>res2a_branch2b ...
### compiling layer group: res2a_branch2a>>res2a_branch2b ... complete.
### compiling layer group: res2b_branch2a>>res2b_branch2b ...
### compiling layer group: res2b_branch2a>>res2b_branch2b ... complete.
### compiling layer group: res3a_branch1 ...
### compiling layer group: res3a_branch1 ... complete.
### compiling layer group: res3a_branch2a>>res3a_branch2b ...
### compiling layer group: res3a_branch2a>>res3a_branch2b ... complete.
### compiling layer group: res3b_branch2a>>res3b_branch2b ...
### compiling layer group: res3b_branch2a>>res3b_branch2b ... complete.
### compiling layer group: res4a_branch1 ...
### compiling layer group: res4a_branch1 ... complete.
### compiling layer group: res4a_branch2a>>res4a_branch2b ...
### compiling layer group: res4a_branch2a>>res4a_branch2b ... complete.
### compiling layer group: res4b_branch2a>>res4b_branch2b ...
### compiling layer group: res4b_branch2a>>res4b_branch2b ... complete.
### compiling layer group: res5a_branch1 ...
### compiling layer group: res5a_branch1 ... complete.
### compiling layer group: res5a_branch2a>>res5a_branch2b ...
### compiling layer group: res5a_branch2a>>res5a_branch2b ... complete.
### compiling layer group: res5b_branch2a>>res5b_branch2b ...
### compiling layer group: res5b_branch2a>>res5b_branch2b ... complete.
### compiling layer group: pool5 ...
### compiling layer group: pool5 ... complete.
### compiling layer group: new_fc ...
### compiling layer group: new_fc ... complete.
### allocating external memory buffers:
offset_name offset_address allocated_space
_______________________ ______________ ________________
"inputdataoffset" "0x00000000" "8.0 mb"
"outputresultoffset" "0x00800000" "4.0 mb"
"schedulerdataoffset" "0x00c00000" "4.0 mb"
"systembufferoffset" "0x01000000" "28.0 mb"
"instructiondataoffset" "0x02c00000" "4.0 mb"
"convweightdataoffset" "0x03000000" "16.0 mb"
"fcweightdataoffset" "0x04000000" "4.0 mb"
"endoffset" "0x04400000" "total: 68.0 mb"
### network compilation complete.
dn = struct with fields:
weights: [1×1 struct]
instructions: [1×1 struct]
registers: [1×1 struct]
syncinstructions: [1×1 struct]
constantdata: {}
ddrinfo: [1×1 struct]
program bitstream onto fpga and download network weights
to deploy the network on the xilinx zcu102 hardware, run the deploy function of the dlhdl.workflow object. this function uses the output of the compile function to program the fpga board by using the programming file. it also downloads the network weights and biases. the deploy function starts programming the fpga device, displays progress messages, and the time it takes to deploy the network.
deploy(hw)
### programming fpga bitstream using ethernet... ### attempting to connect to the hardware board at 192.168.1.101... ### connection successful ### programming fpga device on xilinx soc hardware board at 192.168.1.101... ### copying fpga programming files to sd card... ### setting fpga bitstream and devicetree for boot... # copying bitstream zcu102_int8.bit to /mnt/hdlcoder_rd # set bitstream to hdlcoder_rd/zcu102_int8.bit # copying devicetree devicetree_dlhdl.dtb to /mnt/hdlcoder_rd # set devicetree to hdlcoder_rd/devicetree_dlhdl.dtb # set up boot for reference design: 'axi-stream ddr memory access : 3-axim' ### rebooting xilinx soc at 192.168.1.101... ### reboot may take several seconds... ### attempting to connect to the hardware board at 192.168.1.101... ### connection successful ### programming the fpga bitstream has been completed successfully. ### loading weights to conv processor. ### conv weights loaded. current time is 21-dec-2022 10:45:19 ### loading weights to fc processor. ### fc weights loaded. current time is 21-dec-2022 10:45:19
test network
load the example image.
imgfile = fullfile(pwd,'merchdata','mathworks cube','mathworks cube_0.jpg'); inputimg = imresize(imread(imgfile),[224 224]); imshow(inputimg)
classify the image on the fpga by using the predict method of the dlhdl.workflow object and display the results.
[prediction,speed] = predict(hw,single(inputimg),'profile','on');
### finished writing input activations.
### running single input activation.
deep learning processor profiler performance results
lastframelatency(cycles) lastframelatency(seconds) framesnum total latency frames/s
------------- ------------- --------- --------- ---------
network 7392114 0.02957 1 7394677 33.8
conv1 1115165 0.00446
pool1 199164 0.00080
res2a_branch2a 270125 0.00108
res2a_branch2b 269946 0.00108
res2a 102255 0.00041
res2b_branch2a 269792 0.00108
res2b_branch2b 269902 0.00108
res2b 102695 0.00041
res3a_branch1 155120 0.00062
res3a_branch2a 156480 0.00063
res3a_branch2b 244913 0.00098
res3a 51456 0.00021
res3b_branch2a 245366 0.00098
res3b_branch2b 245123 0.00098
res3b 51286 0.00021
res4a_branch1 135535 0.00054
res4a_branch2a 136117 0.00054
res4a_branch2b 238454 0.00095
res4a 25602 0.00010
res4b_branch2a 237909 0.00095
res4b_branch2b 238282 0.00095
res4b 26742 0.00011
res5a_branch1 324642 0.00130
res5a_branch2a 325897 0.00130
res5a_branch2b 623521 0.00249
res5a 13881 0.00006
res5b_branch2a 624028 0.00250
res5b_branch2b 624631 0.00250
res5b 13051 0.00005
pool5 37083 0.00015
new_fc 17764 0.00007
* the clock frequency of the dl processor is: 250mhz
[val,idx] = max(prediction);
dlquantobj.networkobject.layers(end).classnames{idx}ans = 'mathworks cube'
performance comparison
compare the performance of the quantized network to the performance of the single data type network.
optionsfpga = dlquantizationoptions('bitstream','zcu102_int8','target',htarget); predictionfpga = validate(dlquantobj,imdsvalidation,optionsfpga)
### compiling network for deep learning fpga prototyping ...
### targeting fpga bitstream zcu102_int8.
### optimizing network: fused 'nnet.cnn.layer.batchnormalizationlayer' into 'nnet.cnn.layer.convolution2dlayer'
### the network includes the following layers:
1 'data' image input 224×224×3 images with 'zscore' normalization (sw layer)
2 'conv1' 2-d convolution 64 7×7×3 convolutions with stride [2 2] and padding [3 3 3 3] (hw layer)
3 'conv1_relu' relu relu (hw layer)
4 'pool1' 2-d max pooling 3×3 max pooling with stride [2 2] and padding [1 1 1 1] (hw layer)
5 'res2a_branch2a' 2-d convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
6 'res2a_branch2a_relu' relu relu (hw layer)
7 'res2a_branch2b' 2-d convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
8 'res2a' addition element-wise addition of 2 inputs (hw layer)
9 'res2a_relu' relu relu (hw layer)
10 'res2b_branch2a' 2-d convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
11 'res2b_branch2a_relu' relu relu (hw layer)
12 'res2b_branch2b' 2-d convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
13 'res2b' addition element-wise addition of 2 inputs (hw layer)
14 'res2b_relu' relu relu (hw layer)
15 'res3a_branch2a' 2-d convolution 128 3×3×64 convolutions with stride [2 2] and padding [1 1 1 1] (hw layer)
16 'res3a_branch2a_relu' relu relu (hw layer)
17 'res3a_branch2b' 2-d convolution 128 3×3×128 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
18 'res3a_branch1' 2-d convolution 128 1×1×64 convolutions with stride [2 2] and padding [0 0 0 0] (hw layer)
19 'res3a' addition element-wise addition of 2 inputs (hw layer)
20 'res3a_relu' relu relu (hw layer)
21 'res3b_branch2a' 2-d convolution 128 3×3×128 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
22 'res3b_branch2a_relu' relu relu (hw layer)
23 'res3b_branch2b' 2-d convolution 128 3×3×128 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
24 'res3b' addition element-wise addition of 2 inputs (hw layer)
25 'res3b_relu' relu relu (hw layer)
26 'res4a_branch2a' 2-d convolution 256 3×3×128 convolutions with stride [2 2] and padding [1 1 1 1] (hw layer)
27 'res4a_branch2a_relu' relu relu (hw layer)
28 'res4a_branch2b' 2-d convolution 256 3×3×256 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
29 'res4a_branch1' 2-d convolution 256 1×1×128 convolutions with stride [2 2] and padding [0 0 0 0] (hw layer)
30 'res4a' addition element-wise addition of 2 inputs (hw layer)
31 'res4a_relu' relu relu (hw layer)
32 'res4b_branch2a' 2-d convolution 256 3×3×256 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
33 'res4b_branch2a_relu' relu relu (hw layer)
34 'res4b_branch2b' 2-d convolution 256 3×3×256 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
35 'res4b' addition element-wise addition of 2 inputs (hw layer)
36 'res4b_relu' relu relu (hw layer)
37 'res5a_branch2a' 2-d convolution 512 3×3×256 convolutions with stride [2 2] and padding [1 1 1 1] (hw layer)
38 'res5a_branch2a_relu' relu relu (hw layer)
39 'res5a_branch2b' 2-d convolution 512 3×3×512 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
40 'res5a_branch1' 2-d convolution 512 1×1×256 convolutions with stride [2 2] and padding [0 0 0 0] (hw layer)
41 'res5a' addition element-wise addition of 2 inputs (hw layer)
42 'res5a_relu' relu relu (hw layer)
43 'res5b_branch2a' 2-d convolution 512 3×3×512 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
44 'res5b_branch2a_relu' relu relu (hw layer)
45 'res5b_branch2b' 2-d convolution 512 3×3×512 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
46 'res5b' addition element-wise addition of 2 inputs (hw layer)
47 'res5b_relu' relu relu (hw layer)
48 'pool5' 2-d global average pooling 2-d global average pooling (hw layer)
49 'new_fc' fully connected 5 fully connected layer (hw layer)
50 'prob' softmax softmax (sw layer)
51 'new_classoutput' classification output crossentropyex with 'mathworks cap' and 4 other classes (sw layer)
### notice: the layer 'data' with type 'nnet.cnn.layer.imageinputlayer' is implemented in software.
### notice: the layer 'prob' with type 'nnet.cnn.layer.softmaxlayer' is implemented in software.
### notice: the layer 'new_classoutput' with type 'nnet.cnn.layer.classificationoutputlayer' is implemented in software.
### compiling layer group: conv1>>pool1 ...
### compiling layer group: conv1>>pool1 ... complete.
### compiling layer group: res2a_branch2a>>res2a_branch2b ...
### compiling layer group: res2a_branch2a>>res2a_branch2b ... complete.
### compiling layer group: res2b_branch2a>>res2b_branch2b ...
### compiling layer group: res2b_branch2a>>res2b_branch2b ... complete.
### compiling layer group: res3a_branch1 ...
### compiling layer group: res3a_branch1 ... complete.
### compiling layer group: res3a_branch2a>>res3a_branch2b ...
### compiling layer group: res3a_branch2a>>res3a_branch2b ... complete.
### compiling layer group: res3b_branch2a>>res3b_branch2b ...
### compiling layer group: res3b_branch2a>>res3b_branch2b ... complete.
### compiling layer group: res4a_branch1 ...
### compiling layer group: res4a_branch1 ... complete.
### compiling layer group: res4a_branch2a>>res4a_branch2b ...
### compiling layer group: res4a_branch2a>>res4a_branch2b ... complete.
### compiling layer group: res4b_branch2a>>res4b_branch2b ...
### compiling layer group: res4b_branch2a>>res4b_branch2b ... complete.
### compiling layer group: res5a_branch1 ...
### compiling layer group: res5a_branch1 ... complete.
### compiling layer group: res5a_branch2a>>res5a_branch2b ...
### compiling layer group: res5a_branch2a>>res5a_branch2b ... complete.
### compiling layer group: res5b_branch2a>>res5b_branch2b ...
### compiling layer group: res5b_branch2a>>res5b_branch2b ... complete.
### compiling layer group: pool5 ...
### compiling layer group: pool5 ... complete.
### compiling layer group: new_fc ...
### compiling layer group: new_fc ... complete.
### allocating external memory buffers:
offset_name offset_address allocated_space
_______________________ ______________ ________________
"inputdataoffset" "0x00000000" "12.0 mb"
"outputresultoffset" "0x00c00000" "4.0 mb"
"schedulerdataoffset" "0x01000000" "4.0 mb"
"systembufferoffset" "0x01400000" "28.0 mb"
"instructiondataoffset" "0x03000000" "4.0 mb"
"convweightdataoffset" "0x03400000" "16.0 mb"
"fcweightdataoffset" "0x04400000" "4.0 mb"
"endoffset" "0x04800000" "total: 72.0 mb"
### network compilation complete.
### fpga bitstream programming has been skipped as the same bitstream is already loaded on the target fpga.
### loading weights to conv processor.
### conv weights loaded. current time is 21-dec-2022 10:46:36
### loading weights to fc processor.
### fc weights loaded. current time is 21-dec-2022 10:46:36
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
### finished writing input activations.
### running single input activation.
deep learning processor bitstream build info
resource utilized total percentage
------------------ ---------- ------------ ------------
luts (clb/alm)* 249703 274080 91.11
dsps 391 2520 15.52
block ram 583 912 63.93
* lut count represents configurable logic block(clb) utilization in xilinx devices and adaptive logic module (alm) utilization in intel devices.
### optimizing network: fused 'nnet.cnn.layer.batchnormalizationlayer' into 'nnet.cnn.layer.convolution2dlayer'
### notice: the layer 'data' of type 'imageinputlayer' is split into an image input layer 'data', an addition layer 'data_norm_add', and a multiplication layer 'data_norm' for hardware normalization.
### the network includes the following layers:
1 'data' image input 224×224×3 images with 'zscore' normalization (sw layer)
2 'conv1' 2-d convolution 64 7×7×3 convolutions with stride [2 2] and padding [3 3 3 3] (hw layer)
3 'conv1_relu' relu relu (hw layer)
4 'pool1' 2-d max pooling 3×3 max pooling with stride [2 2] and padding [1 1 1 1] (hw layer)
5 'res2a_branch2a' 2-d convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
6 'res2a_branch2a_relu' relu relu (hw layer)
7 'res2a_branch2b' 2-d convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
8 'res2a' addition element-wise addition of 2 inputs (hw layer)
9 'res2a_relu' relu relu (hw layer)
10 'res2b_branch2a' 2-d convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
11 'res2b_branch2a_relu' relu relu (hw layer)
12 'res2b_branch2b' 2-d convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
13 'res2b' addition element-wise addition of 2 inputs (hw layer)
14 'res2b_relu' relu relu (hw layer)
15 'res3a_branch2a' 2-d convolution 128 3×3×64 convolutions with stride [2 2] and padding [1 1 1 1] (hw layer)
16 'res3a_branch2a_relu' relu relu (hw layer)
17 'res3a_branch2b' 2-d convolution 128 3×3×128 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
18 'res3a_branch1' 2-d convolution 128 1×1×64 convolutions with stride [2 2] and padding [0 0 0 0] (hw layer)
19 'res3a' addition element-wise addition of 2 inputs (hw layer)
20 'res3a_relu' relu relu (hw layer)
21 'res3b_branch2a' 2-d convolution 128 3×3×128 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
22 'res3b_branch2a_relu' relu relu (hw layer)
23 'res3b_branch2b' 2-d convolution 128 3×3×128 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
24 'res3b' addition element-wise addition of 2 inputs (hw layer)
25 'res3b_relu' relu relu (hw layer)
26 'res4a_branch2a' 2-d convolution 256 3×3×128 convolutions with stride [2 2] and padding [1 1 1 1] (hw layer)
27 'res4a_branch2a_relu' relu relu (hw layer)
28 'res4a_branch2b' 2-d convolution 256 3×3×256 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
29 'res4a_branch1' 2-d convolution 256 1×1×128 convolutions with stride [2 2] and padding [0 0 0 0] (hw layer)
30 'res4a' addition element-wise addition of 2 inputs (hw layer)
31 'res4a_relu' relu relu (hw layer)
32 'res4b_branch2a' 2-d convolution 256 3×3×256 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
33 'res4b_branch2a_relu' relu relu (hw layer)
34 'res4b_branch2b' 2-d convolution 256 3×3×256 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
35 'res4b' addition element-wise addition of 2 inputs (hw layer)
36 'res4b_relu' relu relu (hw layer)
37 'res5a_branch2a' 2-d convolution 512 3×3×256 convolutions with stride [2 2] and padding [1 1 1 1] (hw layer)
38 'res5a_branch2a_relu' relu relu (hw layer)
39 'res5a_branch2b' 2-d convolution 512 3×3×512 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
40 'res5a_branch1' 2-d convolution 512 1×1×256 convolutions with stride [2 2] and padding [0 0 0 0] (hw layer)
41 'res5a' addition element-wise addition of 2 inputs (hw layer)
42 'res5a_relu' relu relu (hw layer)
43 'res5b_branch2a' 2-d convolution 512 3×3×512 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
44 'res5b_branch2a_relu' relu relu (hw layer)
45 'res5b_branch2b' 2-d convolution 512 3×3×512 convolutions with stride [1 1] and padding [1 1 1 1] (hw layer)
46 'res5b' addition element-wise addition of 2 inputs (hw layer)
47 'res5b_relu' relu relu (hw layer)
48 'pool5' 2-d global average pooling 2-d global average pooling (hw layer)
49 'new_fc' fully connected 5 fully connected layer (hw layer)
50 'prob' softmax softmax (sw layer)
51 'new_classoutput' classification output crossentropyex with 'mathworks cap' and 4 other classes (sw layer)
### notice: the layer 'prob' with type 'nnet.cnn.layer.softmaxlayer' is implemented in software.
### notice: the layer 'new_classoutput' with type 'nnet.cnn.layer.classificationoutputlayer' is implemented in software.
deep learning processor estimator performance results
lastframelatency(cycles) lastframelatency(seconds) framesnum total latency frames/s
------------- ------------- --------- --------- ---------
network 23502752 0.10683 1 23502752 9.4
data_norm_add 210750 0.00096
data_norm 210750 0.00096
conv1 2164124 0.00984
pool1 515064 0.00234
res2a_branch2a 966221 0.00439
res2a_branch2b 966221 0.00439
res2a 210750 0.00096
res2b_branch2a 966221 0.00439
res2b_branch2b 966221 0.00439
res2b 210750 0.00096
res3a_branch1 540861 0.00246
res3a_branch2a 540749 0.00246
res3a_branch2b 919117 0.00418
res3a 105404 0.00048
res3b_branch2a 919117 0.00418
res3b_branch2b 919117 0.00418
res3b 105404 0.00048
res4a_branch1 503405 0.00229
res4a_branch2a 509261 0.00231
res4a_branch2b 905421 0.00412
res4a 52724 0.00024
res4b_branch2a 905421 0.00412
res4b_branch2b 905421 0.00412
res4b 52724 0.00024
res5a_branch1 1039437 0.00472
res5a_branch2a 1046605 0.00476
res5a_branch2b 2005197 0.00911
res5a 26368 0.00012
res5b_branch2a 2005197 0.00911
res5b_branch2b 2005197 0.00911
res5b 26368 0.00012
pool5 54594 0.00025
new_fc 22571 0.00010
* the clock frequency of the dl processor is: 220mhz
deep learning processor bitstream build info
resource utilized total percentage
------------------ ---------- ------------ ------------
luts (clb/alm)* 168099 274080 61.33
dsps 807 2520 32.02
block ram 453 912 49.67
* lut count represents configurable logic block(clb) utilization in xilinx devices and adaptive logic module (alm) utilization in intel devices.
### finished writing input activations.
### running single input activation.
predictionfpga = struct with fields:
numsamples: 20
metricresults: [1×1 struct]
statistics: [2×7 table]
view the frames per second performance for the quantized network and single-data-type network. the quantized network has a performance of 33.8 frames per second compared to 9.2 frames per second for the single-data-type network. you can use quantization to improve your frames per second performance, however yo could lose accuracy when you quantize your networks.
predictionfpga.statistics.framespersecond
ans = 2×1
9.3606
33.7719
see also
| | | | predict | | | |
related topics
select a web site
choose a web site to get translated content where available and see local events and offers. based on your location, we recommend that you select: .
you can also select a web site from the following list:
americas
- (español)
- (english)
- (english)
europe
- (english)
- (english)
- (deutsch)
- (español)
- (english)
- (français)
- (english)
- (italiano)
- (english)
- (english)
- (english)
- (deutsch)
- (english)
- (english)
- switzerland
- (english)
asia pacific
- (english)
- (english)
- (english)
- 中国
- (日本語)
- (한국어)